© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118402
    Prev
    Next
    INDEX
    Explanations

    file extension or format name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    箋
    -0.87
     ghz
    -0.86
     craft
    -0.85
     cheated
    -0.81
     cromado
    -0.79
     Manten
    -0.78
    儀
    -0.76
     cipolla
    -0.75
    ්‍
    -0.75
     получил
    -0.75
    POSITIVE LOGITS
    Oid
    0.91
    '));
    0.79
    addLast
    0.79
    Explanation
    0.77
    IsRequired
    0.75
    chase
    0.75
    Ҡ
    0.75
    ouro
    0.75
    かせる
    0.75
    て
    0.74
    Activations Density 0.032%

    No Known Activations